AI Inference Engineer — Powering Market-Scale Models

Culturehudson River Trading (hrt); Whitehall; On-site; GBP 189,000 - 227,000; Full time

Job summary

Hudson River Trading (HRT) seeks an AI Research Engineer (Inference) to join the HAIL team in Whitehall, London. You will push large-scale model inference, optimize GPU kernels, and explore devices and data streaming to support trading systems.

You will collaborate with researchers to co-design models and transfer methods across domains, aiming to improve practical AI for markets. CUDA/Triton or FPGA/ASIC experience is valued; LLM familiarity helps but is not required.

Qualifications

• Strong engineering skills with CUDA/Triton/Pallas/CuTe DSL kernel development or lower-level PyTorch/JAX/XLA development.
• Two+ years' experience building deep learning systems across domains.
• Experience translating methods between areas of application is valuable.

Skills

CUDA kernel development

Triton

Pallas

CuTe DSL kernel development

PyTorch development

JAX development

XLA development

CUDA Graphs

FPGA experience

ASIC experience

Deep learning systems

LLM experience

Job description

Hudson River Trading (HRT) seeks an AI Research Engineer (Inference) to join the HAIL team in Whitehall, London. You will push large-scale model inference, optimize GPU kernels, and explore devices and data streaming to support trading systems.

You will collaborate with researchers to co-design models and transfer methods across domains, aiming to improve practical AI for markets. CUDA/Triton or FPGA/ASIC experience is valued; LLM familiarity helps but is not required.